US11790176B2 - Systems and methods for a virtual agent in a cloud computing environment - Google Patents
Systems and methods for a virtual agent in a cloud computing environment Download PDFInfo
- Publication number
- US11790176B2 US11790176B2 US16/431,185 US201916431185A US11790176B2 US 11790176 B2 US11790176 B2 US 11790176B2 US 201916431185 A US201916431185 A US 201916431185A US 11790176 B2 US11790176 B2 US 11790176B2
- Authority
- US
- United States
- Prior art keywords
- topic
- flow
- user
- node
- entities
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
- 238000000034 method Methods 0.000 title claims description 34
- 230000004044 response Effects 0.000 claims abstract description 46
- 230000003993 interaction Effects 0.000 claims abstract description 7
- 230000009471 action Effects 0.000 claims description 10
- 230000000694 effects Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 12
- 238000013515 script Methods 0.000 description 12
- 235000013550 pizza Nutrition 0.000 description 8
- 238000013459 approach Methods 0.000 description 7
- 238000013461 design Methods 0.000 description 7
- 238000003058 natural language processing Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008520 organization Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000001413 cellular effect Effects 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Definitions
- the present disclosure relates generally to natural language understanding (NLU), and more specifically to a NLU virtual agent for a cloud computing environment.
- NLU natural language understanding
- IT information technology
- a respective organization's IT infrastructure may have associated hardware resources (e.g. computing devices, load balancers, firewalls, switches, etc.) and software resources (e.g. productivity software, database applications, custom applications, and so forth).
- hardware resources e.g. computing devices, load balancers, firewalls, switches, etc.
- software resources e.g. productivity software, database applications, custom applications, and so forth.
- Cloud computing relates to the sharing of computing resources that are generally accessed via the Internet.
- a cloud computing infrastructure allows users, such as individuals and/or enterprises, to access a shared pool of computing resources, such as servers, storage devices, networks, applications, and/or other computing based services. By doing so, users are able to access computing resources on demand that are located at remote locations, which resources may be used to perform a variety of computing functions (e.g., storing and/or processing large quantities of computing data).
- cloud computing provides flexibility in accessing cloud computing resources without accruing large up-front costs, such as purchasing expensive network equipment or investing large amounts of time in establishing a private network infrastructure. Instead, by utilizing cloud computing resources, users are able redirect their resources to focus on their enterprise's core functions.
- Such a cloud computing service may host a virtual agent, such as a chat agent, that is designed to automatically respond to issues with the client instance based on natural language requests from a user of the client instance.
- a virtual agent such as a chat agent
- a user may provide a request to a virtual agent for assistance with a password issue, wherein the virtual agent is part of a Natural Language Processing (NLP) or Natural Language Understanding (NLU) system.
- NLP is a general area of computer science and AI that involves some form of processing of natural language input. Examples of areas addressed by NLP include language translation, speech generation, parse tree extraction, part-of-speech identification, and others.
- NLU is a sub-area of NLP that specifically focuses on understanding user utterances.
- NLU natural language processing unit
- a NLU may use algorithms to reduce human language (e.g., spoken or written) into a set of known symbols for consumption by a downstream virtual agent.
- NLP is generally used to interpret free text for further analysis.
- Current approaches to NLP are typically based on deep learning, which is a type of AI that examines and uses patterns in data to improve the understanding of a program.
- Certain simple virtual agents may process natural language requests on a keyword basis.
- certain virtual agents are designed as decision trees that include predefined instructions and responses to certain user utterances.
- such a virtual agent may identify a keyword in a natural language request from a user in a chat dialog, and may respond to the request by repeatedly prompting the user to provide additional details regarding the request until a sufficient amount of information is collected for the virtual agent to take action.
- a simple virtual agent may identify that the user generally intends to update his information based on one or more keywords.
- the simple virtual agent may present the user with a series of prompts (e.g., dialogs with options for the user to interact with using a keyboard and mouse) that enable the user to indicate which piece of information should be updated, as well as to provide the new address details.
- these simple virtual agents may prompt the user to provide information that was previously provided as part of the initial natural language request. Additionally, such simple virtual agents may not be suited to identifying topics or topic changes in the natural language request. As such, it is presently recognized that it is desirable to improve the operation of virtual agents to reduce inefficiencies and to improve the overall user experience.
- Present embodiments are directed to a virtual agent with improved natural language understanding (NLU) capabilities.
- the disclosed virtual agent enables topic selection and topic changes during natural language exchanges with a user. More specifically, the disclosed virtual agent is designed to select suitable topic flows to execute based on intents identified in received user utterances. This can include, for example, the selection of an initial topic flow in response to a topic identified in a first user utterance, as well as switching between topic flows mid-conversation based on identified topic changes. Additionally, when switching from a first topic flow to a second topic flow mid-conversation, the virtual agent determines whether the first topic flow will be resumed upon completion of the second topic flow.
- NLU natural language understanding
- the disclosed virtual agent is also capable of considering all intents and entities conveyed by the user in natural language utterances during the conversation, which enables the virtual agent to avoid prompting the user to provide redundant information. Furthermore, the virtual agent is capable of executing topic flows as part of a global topic flow, which enables the virtual agent to perform a number of predefined activities as part of each interaction with the user, providing a more standardized experience. As such, the disclosed virtual agent improves the performance and usability of the virtual agent, which improves the overall experience of the user when interacting with the virtual agent.
- FIG. 1 is a block diagram of an embodiment of a cloud architecture in which embodiments of the present disclosure may operate;
- FIG. 2 is a schematic diagram of an embodiment of a multi-instance cloud architecture in which embodiments of the present disclosure may operate;
- FIG. 3 is a block diagram of a computing device utilized in a computing system that may be present in FIG. 1 or 2 , in accordance with aspects of the present disclosure;
- FIG. 4 is a block diagram of a portion of an embodiment of a service provider cloud infrastructure that includes a virtual agent, in accordance with aspects of the present disclosure
- FIG. 5 is a flow diagram illustrating an embodiment of a process by which the virtual agent receives and responds to natural language utterances of a user, in accordance with aspects of the present disclosure
- FIG. 6 is a simulated screenshot of an embodiment of a graphical user interface (GUI) that is used to configure NLU topic discovery for the virtual agent, in accordance with aspects of the present disclosure
- FIG. 7 is a simulated screenshot of an embodiment of a GUI that is used to configure a topic flow of the virtual agent, in accordance with aspects of the present disclosure
- FIG. 8 is a simulated screenshot of an embodiment of a GUI that is used to design a topic flow of the virtual agent, in accordance with aspects of the present disclosure
- FIG. 9 is a block diagram of an embodiment of a global topic flow that is executed by the virtual agent, in accordance with aspects of the present disclosure.
- FIG. 10 is a simulated screenshot of an embodiment of a GUI that is used to design the global topic flow of the virtual agent, in accordance with aspects of the present disclosure.
- computing system refers to an electronic computing device such as, but not limited to, a single computer, virtual machine, virtual container, host, server, laptop, and/or mobile device, or to a plurality of electronic computing devices working together to perform the function described as being performed on or by the computing system.
- medium refers to one or more non-transitory, computer-readable physical media that together store the contents described as being stored thereon.
- Embodiments may include non-volatile secondary storage, read-only memory (ROM), and/or random-access memory (RAM).
- an application refers to one or more computing modules, programs, processes, workloads, flows, threads and/or a set of computing instructions executed by a computing system.
- Example embodiments of an application include software modules, software objects, software instances and/or other types of executable code.
- a “flow” refers to a set of actions or instructions (e.g., a portion of an application) that is executed to achieve a particular effect. Flows may be presented in a graphical form in which actions or groups of actions are represented by nodes (e.g., user input nodes, script nodes, decision nodes) in a flow diagram.
- a “topic flow” refers to a flow that is designed to perform one or more actions to address a particular topic or intent of the user.
- an “utterance” refers to a string of natural language text received from a user.
- a “conversation” refers to an exchange of natural language requests and responses between a user and a virtual agent via a particular conversational medium (e.g., chat rooms, email, forum posts, and so forth).
- a particular conversational medium e.g., chat rooms, email, forum posts, and so forth.
- a non-limiting list of example utterances include, chat entries, email subjects, incident descriptions, and so forth.
- an “intent” refers to something indicated in an utterance that a user wants to achieve or accomplish.
- an “entity” refers to something in an utterance that is the subject, object, and/or the context for an intent.
- a “virtual agent” refers to an application that is configured to receive and suitably respond to user utterances based on the intents and entities identified in user utterances.
- Present embodiments are directed to a virtual agent with improved natural language understanding (NLU) capabilities.
- the disclosed virtual agent enables topic selection and topic changes during natural language conversations with a user. More specifically, the disclosed virtual agent is designed to select suitable topic flows to execute based on intents identified in received user utterances. Additionally, when switching from a first topic flow to a second topic flow mid-conversation, the virtual agent determines whether the first topic flow is resumed upon completion of the second topic flow. Furthermore, the disclosed virtual agent is capable of storing and applying all intents conveyed by the user in natural language requests during the conversation with the virtual agent, which enables the virtual agent to avoid prompting the user to provide redundant information.
- NLU natural language understanding
- the disclosed virtual agent supports the creation and execution of a global topic flow, which can enable all interactions with the virtual agent to follow a predefined and customizable pattern. As such, the disclosed virtual agent improves the performance and usability of the virtual agent, which improves the overall experience of the user.
- FIG. 1 a schematic diagram of an embodiment of a cloud computing system 10 where embodiments of the present disclosure may operate, is illustrated.
- the cloud computing system 10 may include a client network 12 , a network 14 (e.g., the Internet), and a cloud-based platform 16 .
- the cloud-based platform 16 may be a configuration management database (CMDB) platform.
- CMDB configuration management database
- the client network 12 may be a local private network, such as local area network (LAN) having a variety of network devices that include, but are not limited to, switches, servers, and routers.
- LAN local area network
- the client network 12 represents an enterprise network that could include one or more LANs, virtual networks, data centers 18 , and/or other remote networks. As shown in FIG. 1 , the client network 12 is able to connect to one or more client devices 20 A, 20 B, and 20 C so that the client devices are able to communicate with each other and/or with the network hosting the platform 16 .
- the client devices 20 may be computing systems and/or other types of computing devices generally referred to as Internet of Things (IoT) devices that access cloud computing services, for example, via a web browser application or via an edge device 22 that may act as a gateway between the client devices 20 and the platform 16 .
- FIG. 1 also illustrates that the client network 12 includes an administration or managerial device, agent, or server, such as a management, instrumentation, and discovery (MID) server 24 that facilitates communication of data between the network hosting the platform 16 , other external applications, data sources, and services, and the client network 12 .
- the client network 12 may also include a connecting network device (e.g., a gateway or router) or a combination of devices that implement a customer firewall or intrusion protection system.
- FIG. 1 illustrates that client network 12 is coupled to a network 14 .
- the network 14 may include one or more computing networks, such as other LANs, wide area networks (WAN), the Internet, and/or other remote networks, to transfer data between the client devices 20 and the network hosting the platform 16 .
- Each of the computing networks within network 14 may contain wired and/or wireless programmable devices that operate in the electrical and/or optical domain.
- network 14 may include wireless networks, such as cellular networks (e.g., Global System for Mobile Communications (GSM) based cellular network), IEEE 802.11 networks, and/or other suitable radio-based networks.
- the network 14 may also employ any number of network communication protocols, such as Transmission Control Protocol (TCP) and Internet Protocol (IP).
- TCP Transmission Control Protocol
- IP Internet Protocol
- network 14 may include a variety of network devices, such as servers, routers, network switches, and/or other network hardware devices configured to transport data over the network 14 .
- the network hosting the platform 16 may be a remote network (e.g., a cloud network) that is able to communicate with the client devices 20 via the client network 12 and network 14 .
- the network hosting the platform 16 provides additional computing resources to the client devices 20 and/or the client network 12 .
- users of the client devices 20 are able to build and execute applications for various enterprise, IT, and/or other organization-related functions.
- the network hosting the platform 16 is implemented on the one or more data centers 18 , where each data center could correspond to a different geographic location.
- Each of the data centers 18 includes a plurality of virtual servers 26 (also referred to herein as application nodes, application servers, virtual server instances, application instances, or application server instances), where each virtual server 26 can be implemented on a physical computing system, such as a single electronic computing device (e.g., a single physical hardware server) or across multiple-computing devices (e.g., multiple physical hardware servers).
- virtual servers 26 include, but are not limited to a web server (e.g., a unitary Apache installation), an application server (e.g., unitary JAVA Virtual Machine), and/or a database server (e.g., a unitary relational database management system (RDBMS) catalog).
- a web server e.g., a unitary Apache installation
- an application server e.g., unitary JAVA Virtual Machine
- database server e.g., a unitary relational database management system (RDBMS) catalog
- network operators may choose to configure the data centers 18 using a variety of computing infrastructures.
- one or more of the data centers 18 are configured using a multi-tenant cloud architecture, such that one of the server instances 26 handles requests from and serves multiple customers.
- Data centers 18 with multi-tenant cloud architecture commingle and store data from multiple customers, where multiple customer instances are assigned to one of the virtual servers 26 .
- the particular virtual server 26 distinguishes between and segregates data and other information of the various customers.
- a multi-tenant cloud architecture could assign a particular identifier for each customer in order to identify and segregate the data from each customer.
- implementing a multi-tenant cloud architecture may suffer from various drawbacks, such as a failure of a particular one of the server instances 26 causing outages for all customers allocated to the particular server instance.
- one or more of the data centers 18 are configured using a multi-instance cloud architecture to provide every customer its own unique customer instance or instances.
- a multi-instance cloud architecture could provide each customer instance with its own dedicated application server and dedicated database server.
- the multi-instance cloud architecture could deploy a single physical or virtual server 26 and/or other combinations of physical and/or virtual servers 26 , such as one or more dedicated web servers, one or more dedicated application servers, and one or more database servers, for each customer instance.
- multiple customer instances could be installed on one or more respective hardware servers, where each customer instance is allocated certain portions of the physical server resources, such as computing memory, storage, and processing power.
- each customer instance has its own unique software stack that provides the benefit of data isolation, relatively less downtime for customers to access the platform 16 , and customer-driven upgrade schedules.
- An example of implementing a customer instance within a multi-instance cloud architecture will be discussed in more detail below with reference to FIG. 2 .
- FIG. 2 is a schematic diagram of an embodiment of a multi-instance cloud architecture 100 where embodiments of the present disclosure may operate.
- FIG. 2 illustrates that the multi-instance cloud architecture 100 includes the client network 12 and the network 14 that connect to two (e.g., paired) data centers 18 A and 18 B that may be geographically separated from one another.
- network environment and service provider cloud infrastructure client instance 102 (also referred to herein as a client instance 102 ) is associated with (e.g., supported and enabled by) dedicated virtual servers (e.g., virtual servers 26 A, 26 B, 26 C, and 26 D) and dedicated database servers (e.g., virtual database servers 104 A and 104 B).
- dedicated virtual servers e.g., virtual servers 26 A, 26 B, 26 C, and 26 D
- dedicated database servers e.g., virtual database servers 104 A and 104 B.
- the virtual servers 26 A- 26 D and virtual database servers 104 A and 104 B are not shared with other client instances and are specific to the respective client instance 102 .
- the virtual servers 26 A- 26 D and virtual database servers 104 A and 104 B are allocated to two different data centers 18 A and 18 B so that one of the data centers 18 acts as a backup data center.
- Other embodiments of the multi-instance cloud architecture 100 could include other types of dedicated virtual servers, such as a web server.
- the client instance 102 could be associated with (e.g., supported and enabled by) the dedicated virtual servers 26 A- 26 D, dedicated virtual database servers 104 A and 104 B, and additional dedicated virtual web servers (not shown in FIG. 2 ).
- FIGS. 1 and 2 illustrate specific embodiments of a cloud computing system 10 and a multi-instance cloud architecture 100 , respectively, the disclosure is not limited to the specific embodiments illustrated in FIGS. 1 and 2 .
- FIG. 1 illustrates that the platform 16 is implemented using data centers
- other embodiments of the platform 16 are not limited to data centers and can utilize other types of remote network infrastructures.
- other embodiments of the present disclosure may combine one or more different virtual servers into a single virtual server or, conversely, perform operations attributed to a single virtual server using multiple virtual servers.
- the virtual servers 26 A, 26 B, 26 C, 26 D and virtual database servers 104 A, 104 B may be combined into a single virtual server.
- FIGS. 1 and 2 are only examples to facilitate ease of description and explanation and are not intended to limit the disclosure to the specific examples illustrated therein.
- FIGS. 1 and 2 incorporate computing systems of various types (e.g., servers, workstations, client devices, laptops, tablet computers, cellular telephones, and so forth) throughout.
- computing systems of various types (e.g., servers, workstations, client devices, laptops, tablet computers, cellular telephones, and so forth) throughout.
- a brief, high level overview of components typically found in such systems is provided.
- the present overview is intended to merely provide a high-level, generalized view of components typical in such computing systems and should not be viewed as limiting in terms of components discussed or omitted from discussion.
- the present approach may be implemented using one or more processor-based systems such as shown in FIG. 3 .
- applications and/or databases utilized in the present approach may be stored, employed, and/or maintained on such processor-based systems.
- such systems as shown in FIG. 3 may be present in a distributed computing environment, a networked environment, or other multi-computer platform or architecture.
- systems such as that shown in FIG. 3 may be used in supporting or communicating with one or more virtual environments or computational instances on which the present approach may be implemented.
- FIG. 3 generally illustrates a block diagram of example components of a computing system 200 and their potential interconnections or communication paths, such as along one or more busses.
- the computing system 200 may include various hardware components such as, but not limited to, one or more processors 202 , one or more busses 204 , memory 206 , input devices 208 , a power source 210 , a network interface 212 , a user interface 214 , and/or other computer components useful in performing the functions described herein.
- the one or more processors 202 may include one or more microprocessors capable of performing instructions stored in the memory 206 . Additionally or alternatively, the one or more processors 202 may include application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), and/or other devices designed to perform some or all of the functions discussed herein without calling instructions from the memory 206 .
- ASICs application-specific integrated circuits
- FPGAs field-programmable gate arrays
- the one or more busses 204 include suitable electrical channels to provide data and/or power between the various components of the computing system 200 .
- the memory 206 may include any tangible, non-transitory, and computer-readable storage media. Although shown as a single block in FIG. 1 , the memory 206 can be implemented using multiple physical units of the same or different types in one or more physical locations.
- the input devices 208 correspond to structures to input data and/or commands to the one or more processors 202 .
- the input devices 208 may include a mouse, touchpad, touchscreen, keyboard and the like.
- the power source 210 can be any suitable source for power of the various components of the computing device 200 , such as line power and/or a battery source.
- the network interface 212 includes one or more transceivers capable of communicating with other devices over one or more networks (e.g., a communication channel).
- the network interface 212 may provide a wired network interface or a wireless network interface.
- a user interface 214 may include a display that is configured to display text or images transferred to it from the one or more processors 202 .
- the user interface 214 may include other devices for interfacing with a user, such as lights (e.g., LEDs), speakers, and the like.
- FIG. 4 illustrates an example of a portion of a service provider cloud infrastructure, including the cloud-based platform 16 discussed above.
- the cloud-based platform 16 is connected to a client device 20 via the network 14 to provide a user interface to network applications executing within the client instance 102 (e.g., via a web browser of the client device 20 ).
- Cloud provider infrastructures are generally configured to support a plurality of end-user devices, such as client device 20 , concurrently, wherein each end-user device is in communication with the single client instance 102 .
- cloud provider infrastructures may be configured to support any number of client instances, such as client instance 102 , concurrently, with each of the instances in communication with one or more end-user devices.
- an end-user may also interface with client instance 102 using an application that is executed within a web browser.
- the client instance 102 is communicatively coupled to a shared instance 220 of the cloud-based platform 16 .
- the shared instance 220 hosts a NLU service 222 that can be used by any suitable number of client instances to provide NLU functionality.
- the NLU service 222 is capable of analyzing a collection or corpus of utterances (e.g., chat sessions, email exchanges, forum posts, and so forth) stored by the database server 104 of the client instance 102 to generate one or more NLU models 224 , which may also be referred to herein as intent/entity models.
- the NLU models 224 may be manually created by a developer or designer.
- a “NLU model” is a collection of intents and entities that are defined alongside sample utterances of these intents and entities.
- these NLU models 224 may be stored by a database server 104 of the client instance 102 , as illustrated in FIG. 4 . It may be appreciated that, in other embodiments, the NLU service 222 may be an external service that is communicatively coupled to the client instance 102 via the network 14 .
- the client instance 102 includes a virtual agent 225 that is designed to receive a natural language request as an utterance 226 from a user of the client device 20 and to respond accordingly.
- the response of the virtual agent 225 may include performing actions within the client instance 102 and/or providing a response 228 or confirmation message to the user of the client device 20 .
- the utterance 226 and/or response 228 may be in the form of a written natural language request, such as a chat messages, email messages, forum posts, and so forth.
- the client instance 102 includes a NLU interface application programming interface (API) 230 that enables the virtual agent 225 to provide the received utterance 226 and NLU models 224 to the NLU service 222 for processing.
- API application programming interface
- the NLU service 222 searches the NLU models 224 for intents and entities indicated in the utterance 226 based on the sample utterances stored in the NLU models 224 .
- the NLU service 222 provides a scored set (e.g., a list or table) of intents and entities identified in the utterance 226 to the virtual agent 225 , wherein the scored set of intents and entities includes corresponding confidence scores for each of the identified intents and/or entities.
- the virtual agent 225 is designed to execute particular topic flows in response to certain intents and/or entities being identified in the user utterance 226 at different points in the conversation.
- FIG. 5 is a flow diagram illustrating an embodiment of a process 240 by which the virtual agent 225 receives and responds to natural language utterances of a user.
- the process 240 may be stored in at least one suitable memory (e.g., memory 206 ) and executed by at least one suitable processor (e.g., processor 202 ) associated with the cloud-based platform 16 .
- the process 240 may include additional steps, omitted steps, repeated steps, and so forth, in accordance with the present disclosure. Additionally, the process 240 of FIG. 5 is discussed with reference to elements of FIG. 4 .
- the embodiment of the process 240 illustrated in FIG. 5 begins with the virtual agent 225 receiving (block 242 ) a natural language request as a user utterance 226 .
- the virtual agent 225 may be a chat virtual agent, and the received user utterance 226 may be a chat message from a user of the client device 20 .
- the virtual agent provides (block 244 ) the user utterance 226 and one or more of the NLU models 224 to the NLU service 222 for processing, wherein the NLU service 222 identifies and scores intent and entities of the user utterance 226 based on the NLU models 224 .
- the virtual agent receives (block 246 ) the scored set of intents and entities 248 from the NLU service 222 for the user utterance 226 .
- the virtual agent 225 determines (block 250 ) whether the identified intents correspond to a current topic flow of the virtual agent 225 .
- a virtual agent 225 may include a topic flow for ordering products, a topic flow for checking the status of orders, a topic flow for updating user account information, and so forth.
- each topic flow is associated with a particular intent defined in the NLU models 224 .
- the virtual agent 225 determines that an intent of the received set of scored intents and entities does not correspond to a currently executing topic flow, then the virtual agent 225 responds by switching (block 252 ) to and executing another topic flow.
- the virtual agent 225 identifies another topic flow that is associated with an intent of the received set of scored intents and entities 248 , and begins execution of this topic flow. As discussed below, depending on the design of the topic flow, the virtual agent 225 may or may not resume execution of the original topic flow at the conclusion of the new topic flow.
- the process 240 continues with the virtual agent 225 applying (block 254 ) entities from the scored set of intents and entities 248 to the selected topic flow. That is, rather than prompting the user for information that was already provided as part of the utterance 226 or previous utterances of the conversation, the virtual agent 225 applies this entity data to various data input nodes of the topic flow. For example, if an initial user utterance includes a statement, “I would like to order a pepperoni pizza,” then the virtual agent 225 may identify an intent to order food in decision block 250 , and switch to an “Order pizza” topic flow in block 252 .
- the “Order pizza” topic flow may include a number of data input nodes designed to collect information from the user regarding the type of pizza, the type of pizza crust, toppings to be included, and so forth. However, since the user utterance 226 already included an entity indicating a desire for pepperoni toppings, this entity is applied to the corresponding input nodes of the “Order pizza” flow. As such, when the virtual agent 225 is executing the “Order pizza” topic flow, the virtual agent 225 will not prompt the user to repeat aspects of the order when these input nodes are reached, and will only prompt the user to provide data for input nodes that have not yet been satisfied, such as asking about the type of pizza or the type of crust.
- the virtual agent 225 may additionally store the entity data from previously received user utterances (e.g., user utterances that are part of the same conversation). For such embodiments, the virtual agent 225 may also apply this entity data from the previously received user utterances to the selected topic flow to avoid requesting information already received from the user.
- previously received user utterances e.g., user utterances that are part of the same conversation.
- the virtual agent 225 may also apply this entity data from the previously received user utterances to the selected topic flow to avoid requesting information already received from the user.
- the process 240 continues with the virtual agent 225 performing (block 256 ) one or more actions based on the current topic flow.
- the topic flow may execute as designed to address the request indicated in the user utterance 226 .
- the virtual agent 225 may respond by performing actions within the client instance 102 , such as creating, updating, or deleting records stored by the database server 104 , executing other defined flows or scripts, communicating with external services, and so forth.
- the virtual agent 225 may additionally or alternatively provide the response 228 or confirmation message to the client device 20 D indicating that that the user utterance 226 was received and/or that certain actions were performed.
- the virtual agent 225 may respond by prompting the user to provide additional data for input blocks that were not satisfied by the entities from the received user utterance 226 . As indicated by the arrow 258 , in certain embodiments, the virtual agent 225 may subsequently receive another utterance from the user and repeat the process 240 .
- FIG. 6 is a simulated screenshot of an embodiment of a graphical user interface (GUI) 270 that is used to configure NLU topic discovery for the virtual agent 225 .
- GUI graphical user interface
- the GUI 270 may be hosted by the client instance 102 and accessed via a web browser application of the client device 20 D.
- the data received and presented by the GUI 270 may be stored in one or more suitable database tables (e.g., a NLU_Settings table, a Topic_Properties table, a Topic_Flow table, a Global_Topic_Flow table, etc.) of the database server 104 .
- suitable database tables e.g., a NLU_Settings table, a Topic_Properties table, a Topic_Flow table, a Global_Topic_Flow table, etc.
- the GUI 270 illustrated in FIG. 6 includes a “Topic discovery with NLU” switch or checkbox 272 .
- the virtual agent 225 when the switch 272 is not selected or activated, then the virtual agent 225 performs topic discovery on a keyword basis, as discussed above. However, when the switch 272 is selected or activated, then the virtual agent 225 is configured to process user utterances using an embodiment of the process 240 of FIG. 5 .
- the illustrated GUI 270 also includes a “NLU API” dropdown list 274 that is designed to receive and present a developer selection of a NLU provider from a predefined list of different NLU providers (e.g., PARLO, IBM WATSON, AMAZON ALEXA).
- the NLU provider indicated by the dropdown list 274 will be provided received user utterances, along with one or more NLU models 224 , in order to generate the scored set of intents and entities 248 , as discussed above.
- the illustrated GUI 270 also includes a “Confident score” field 276 that is designed to receive and present a real number value between zero and one that represents the confidence threshold value for topic identification. That is, only when a confidence score of an intent in the scored set of intents and entities 248 is above the confidence threshold value, will the virtual agent 225 switch to executing the topic flow associated with this intent.
- FIG. 7 is a simulated screenshot of an embodiment of a GUI 280 that is used to configure a topic flow of the virtual agent 225 .
- the illustrated GUI 280 includes a “Topic Name” field 282 designed to receive and present a string value that corresponds the topic name, as well as a “Description” field 284 designed to receive and present a string value that corresponds the topic description of the topic flow.
- the illustrated GUI 280 includes a “Topic Category” dropdown list 286 that is designed to receive and present a developer selection of a category of the topic flow from a predefined list of potential categories (e.g., a human resources category, a computer support category, and so forth) for the topic flow being configured.
- potential categories e.g., a human resources category, a computer support category, and so forth
- the illustrated GUI 280 includes a “NLU model” dropdown list 288 that is designed to receive and present a NLU model selection from a predefined list of available NLU models 224 (e.g., IT topics, Human Resources topics, Product Order topics, etc.) to be used by the NLU service 222 to process user utterances within the topic flow.
- the illustrated GUI 280 includes an “Intent for topic discovery” dropdown list 290 that is designed to receive and present a selected intent from a predefined list of intents that are defined within the selected NLU model, as indicated by the dropdown list 288 .
- the illustrated GUI 280 includes a text label 292 indicating the entities that are defined associated with the selected intent within the selected NLU model.
- the GUI 280 of FIG. 7 may include additional elements that enable a designer to further control the execution of the topic flow.
- the illustrated GUI 280 includes a “Condition” button 294 that enables the designer to establish a predefined set of conditions that are to be met before the topic flow can be executed.
- the illustrated GUI 280 includes a “Role” button 296 that enables the designer to identify particular roles or user accounts of the client instance 102 that are authorized to provoke execution of the topic flow.
- the illustrated GUI 280 includes a “Live Agent Condition” button 298 that enables the designer to define conditions (e.g., the receipt of certain intents and/or entities) during the execution of the topic flow that, when met, prompts the virtual agent 225 to hand off the conversation to a live agent.
- the GUI 280 may also include a “Resume Topic Flow If Switched” checkbox that is designed to receive and present a Boolean value indicating whether the virtual agent 225 will return and resume execution of the topic flow when the virtual agent 225 switches to a different topic flow mid-conversation.
- FIG. 8 is a simulated screenshot of an embodiment of a GUI 310 that is used to design a topic flow 312 of the virtual agent 225 .
- the illustrated GUI 280 includes a flow section 314 that visually depicts a portion of the example topic flow 282 .
- the illustrated GUI 310 also includes a properties section 316 that lists properties of a selected node in the flow section 312 of the GUI 310 .
- the illustrated portion of the example topic flow 312 includes a currently selected user input node “Items to Order” 318 , and as such, the properties for this element are presented in the properties section 316 of the GUI 310 .
- the properties section 316 of the GUI 310 includes a “Name” field 320 that is designed to receive and present a string value that represents a name of the topic flow.
- the properties section 316 of the illustrated GUI 310 also includes a “Variable Name” field 322 designed to receive and present a string value that defines the name of a variable within the topic flow that is assigned a value in response to data input from the user.
- the properties section 316 of the illustrated GUI 310 includes a “Prompt” field 324 designed to receive and present a string value that defines the text that the virtual agent 225 may provide to the user to request the information associated with the user input node.
- prompts may be questions that are presented to the user to provoke a natural language response from the user
- other prompts may include user interface elements (e.g., buttons, checkboxes, drop down lists, etc.) that receive input from the user (e.g., via a mouse, keyboard, touchscreen, etc.).
- user interface elements e.g., buttons, checkboxes, drop down lists, etc.
- the properties section 316 of the GUI 310 includes an “Associated Entity” dropdown list 326 designed to receive and present a designer selection from entities that are defined in the NLU model associated with the topic flow, as discussed above with respect to FIG. 7 .
- the properties section 316 of the illustrated GUI 310 also includes a “Skip node if the entity is fulfilled” checkbox 328 that is designed to receive and present a Boolean value (e.g., selected, unselected) indicating whether or not the entity selected in dropdown list 326 should be applied to populate the selected user input node 318 when the entity has been identified in a user utterance 226 .
- the topic flow 312 will apply this entity value as the input data to the input node 318 , and then proceed to execute the next node in the topic flow.
- the “Skip node if the entity is fulfilled” checkbox 328 is not selected, or when it is selected and the @desktop entity is not defined within a previously received user utterance, then the input node will prompt the user for the data of the user input node based on the value indicated by the “Prompt” field 324 .
- the properties section 316 of the GUI 310 includes a “With NLU User Input” checkbox 330 designed to receive and present a Boolean value (e.g., selected, unselected) indicating whether or not the virtual agent 225 will allow the user to respond to the prompt using a natural language utterance. For example, when this checkbox 330 is selected and the associated entity is not identified in a previously received utterance, then the virtual agent 225 prompts the user with the value indicated by the “Prompt” field 324 , and enables the user to respond by providing a natural language utterance.
- a Boolean value e.g., selected, unselected
- the virtual agent 225 provides the user with the text indicated by the “Prompt” field 324 , and provides user interface elements (e.g., buttons, checkboxes, dropdown lists) with which the user can interact to respond to the prompt.
- user interface elements e.g., buttons, checkboxes, dropdown lists
- the properties section 316 of the GUI 310 includes an “Acknowledge Message” field 332 designed to receive and present a string value representing a message that the virtual agent 225 will send to the user in response to successfully receiving the user input data from the user.
- the properties section 316 of the GUI 310 includes a “Default Value” field 334 designed to receive and present a default value that the virtual agent 225 assigns to the “ItemsToOrder” variable indicated in field 322 when the data is not received from the prompted user.
- the properties section 316 of the GUI 310 includes a “Confirmation Message” field designed to receive and present a string value representing a message that the virtual agent 225 sends to the user to confirm the input provided by the user in response to the entity associated with the user input node 318 having a corresponding confidence score that is below a defined confidence threshold value.
- the virtual agent 225 may include a global topic flow that defines a set of steps to be performed by the virtual agent 225 as part of the execution of all topic flows.
- FIG. 9 is a block diagram of an embodiment of a global topic flow 340 that is executed by the virtual agent 225 .
- the illustrated global topic flow 340 defines certain activities that will occur for every natural language exchange that the virtual agent 225 has with a user, such that the overall conversational structure can be standardized and uniform across all user interactions with the virtual agent 225 .
- the global topic flow 340 provides a centralized flow that can be adjusted by a developer to modify the conversational structure and the behavior of the virtual agent 225 for all conversations.
- the global topic flow 340 begins with a “Greetings” output node 342 that is configured to output a greeting to the user.
- a developer can customize the output of this node, such that all conversations with the virtual agent 225 begin with the same suitable greeting message.
- the developer may configure the “Greetings” output node 342 to output a message, such as, “Hi @user name, I see you have @task_count tasks listed for today. How can I help you?”
- the illustrated embodiment of the global topic flow 340 continues with a “Topic Picker Control” user input node 344 that is configured to receive a user utterance in response to the greeting message.
- the illustrated embodiment of the global topic flow 340 includes a “Topic Discovery” script node 346 that is configured to identify and execute suitable topic flows based on the received user utterance. That is, as discussed above with respect to FIG. 5 , the virtual agent 225 receives the user utterance, provides the user utterance to the NLU service 222 for processing, and receives the score set of intents and entities 248 from the NLU service 222 .
- the virtual agent 225 attempts to identify a topic flow to execute based on a suitably high-confidence intent of the set of scored intents and entities 248 that is associated with the topic flow, as discussed above with respect to FIG. 7 .
- the virtual agent 225 switches to and begins execution of the identified topic flow.
- the “Topic Discovery” script node 346 handles topic discovery, topic switching, and topic flow execution, as discussed above with respect to FIG. 5 .
- the “Topic Discovery” script node 346 may include instructions that define how topic switching should commence, such as whether the original topic flow is resumed after completion of the switched topic flow.
- the “Topic Discovery” script node 346 also includes instructions that prompt the virtual agent 225 to execute an error topic flow in the event that the scored set of intents and entities 248 does not include a suitably high-confidence intent that is associated with a particular topic flow. In certain embodiments, the “Topic Discovery” script node 346 also handles switching to a live agent topic flow that routes the user utterance to a live agent to resume interactions with the user, such as in the event that a live agent is requested by the user.
- the illustrated embodiment of the global topic flow 340 continues with an “Anything else?” user input node 348 (also referred to herein as an additional topics input node) configured to prompt the user and receive input (e.g., a natural language utterance) indicating whether or not the user would like to address another topic.
- user input node 348 also referred to herein as an additional topics input node
- receive input e.g., a natural language utterance
- the prompt may be a question that presented to the user to provoke a natural language response from the user (e.g., “Do you have any other requests?”), while other prompts may include user interface elements (e.g., a “Yes” button and a “No” button) that receive non-natural language input from the user (e.g., via a mouse, keyboard, touchscreen, etc.).
- a natural language response e.g., “Do you have any other requests?”
- other prompts may include user interface elements (e.g., a “Yes” button and a “No” button) that receive non-natural language input from the user (e.g., via a mouse, keyboard, touchscreen, etc.).
- the virtual agent 225 processes the response of the user and continues to a decision node 350 , wherein the virtual agent 225 determines whether the received user input indicates additional topics to be discussed.
- the virtual agent 225 returns to the “Topic Picker Control” user input node 344 , as indicated by the arrow 352 .
- the virtual agent 225 may use the NLU service 222 to process the user utterance, as discussed above, to identify a suitably high-confidence intent that is associated with particular topic flows. As such, for these embodiments, the virtual agent 225 may apply the identified intent to the “Topic Picker Control” user input node 344 and proceed to the “Topic Discovery” script node 346 , rather than prompting the user for additional topics to discuss.
- the virtual agent 225 may proceed to a “Survey” script node 354 configured to prompt the user with one or more questions about the user's experience using the virtual agent 225 .
- the “Survey” script node 354 is further configured to receive user input in response to the prompt, and to store the user's response for review by the developer during continued development of the system.
- the virtual agent 225 concludes execution of the global topic flow 340 .
- FIG. 10 is a simulated screenshot of an embodiment of a GUI 360 that is used to design a global topic flow (e.g., the global topic flow 340 of FIG. 9 ) for the virtual agent 225 .
- a global topic flow e.g., the global topic flow 340 of FIG. 9
- the illustrated GUI 360 includes a “Welcome topic” dropdown menu 362 that is designed to receive and present a developer selection of a topic flow to be executed at the beginning of the global topic flow, such as by the “Greetings” output node 342 of the global topic flow 340 illustrated in FIG. 9 .
- the illustrated GUI 360 includes a “Survey topic” dropdown menu 364 is designed to receive and present a developer selection of a topic flow to be executed at the end of the global topic flow, such as by the “Survey” script node 354 illustrated in FIG. 9 .
- GUI 360 illustrated in FIG. 10 includes additional fields for defining additional topic flows to be executed in response to different conditions during execution of the global topic flow.
- the illustrated GUI 360 includes a “Live Agent topic” dropdown menu 366 that is designed to receive and present a developer selection of a topic flow that is executed in response to the user requesting to interact with a live agent during execution of the global topic flow.
- the “Explore help topic” dropdown menu 368 is designed to receive and present a developer selection of a topic flow that is executed in response to the user requesting help regarding how to interact with the virtual agent 225 .
- the “Error Topic” dropdown menu 370 is designed to receive and present a developer selection of a topic flow that is executed in response to an error being encountered while executing the global topic flow.
- the “Closing topic” dropdown menu 372 is designed to receive and present a developer selection of a topic flow that may be executed prior to the topic flow indicated by the “Survey topic” dropdown menu 354 .
- the “Fallback topic” dropdown menu 374 is designed to receive and present a developer selection of a topic flow that may be executed when the virtual agent 225 is unable to identify a corresponding topic flow in response to a user utterance.
- the “Anything else” dropdown menu 376 is designed to receive and present a developer selection of a topic flow that may be executed as part of the “Anything else?” user input node 348 to determine whether the user has additional requests to process.
- the technical effects of the present disclosure include a virtual agent with improved natural language understanding (NLU) capabilities.
- the disclosed virtual agent enables topic selection and topic changes during natural language conversations with a user. More specifically, the disclosed virtual agent is designed to select suitable topic flows to execute based on intents identified in received user utterances. Furthermore, the disclosed virtual agent is capable of storing and applying all intents conveyed by the user in natural language requests during the conversation with the virtual agent, which enables the virtual agent to avoid prompting the user to provide redundant information. Additionally, the disclosed virtual agent supports the creation and execution of a global topic flow, which can enable all interactions with the virtual agent to follow a predefined and customizable pattern. As such, the disclosed virtual agent improves the performance and usability of the virtual agent, which improves the overall experience of the user.
- NLU natural language understanding
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Information Transfer Between Computers (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
Claims (20)
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/431,185 US11790176B2 (en) | 2019-03-19 | 2019-06-04 | Systems and methods for a virtual agent in a cloud computing environment |
KR1020217033770A KR102623476B1 (en) | 2019-03-19 | 2020-03-19 | Systems and methods for virtual agents in a cloud computing environment |
PCT/US2020/023682 WO2020191219A1 (en) | 2019-03-19 | 2020-03-19 | Systems and methods for a virtual agent in a cloud computing environment |
JP2021556537A JP7344310B2 (en) | 2019-03-19 | 2020-03-19 | Systems and methods for virtual agents in cloud computing environments |
AU2020240106A AU2020240106B2 (en) | 2019-03-19 | 2020-03-19 | Systems and methods for a virtual agent in a cloud computing environment |
US18/462,092 US20230409837A1 (en) | 2019-03-19 | 2023-09-06 | Systems and methods for a virtual agent in a cloud computing environment |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201962820736P | 2019-03-19 | 2019-03-19 | |
US16/431,185 US11790176B2 (en) | 2019-03-19 | 2019-06-04 | Systems and methods for a virtual agent in a cloud computing environment |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US18/462,092 Continuation US20230409837A1 (en) | 2019-03-19 | 2023-09-06 | Systems and methods for a virtual agent in a cloud computing environment |
Publications (2)
Publication Number | Publication Date |
---|---|
US20200302020A1 US20200302020A1 (en) | 2020-09-24 |
US11790176B2 true US11790176B2 (en) | 2023-10-17 |
Family
ID=72513622
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/431,185 Active 2041-02-13 US11790176B2 (en) | 2019-03-19 | 2019-06-04 | Systems and methods for a virtual agent in a cloud computing environment |
US18/462,092 Pending US20230409837A1 (en) | 2019-03-19 | 2023-09-06 | Systems and methods for a virtual agent in a cloud computing environment |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US18/462,092 Pending US20230409837A1 (en) | 2019-03-19 | 2023-09-06 | Systems and methods for a virtual agent in a cloud computing environment |
Country Status (5)
Country | Link |
---|---|
US (2) | US11790176B2 (en) |
JP (1) | JP7344310B2 (en) |
KR (1) | KR102623476B1 (en) |
AU (1) | AU2020240106B2 (en) |
WO (1) | WO2020191219A1 (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220310079A1 (en) * | 2019-07-18 | 2022-09-29 | Sri International | The conversational assistant for conversational engagement |
US11140042B2 (en) * | 2019-09-18 | 2021-10-05 | Servicenow, Inc. | Dictionary-based service mapping |
JP7420109B2 (en) * | 2021-04-08 | 2024-01-23 | トヨタ自動車株式会社 | Information output system, server device and information output method |
US11893401B1 (en) * | 2022-12-06 | 2024-02-06 | Capital One Services, Llc | Real-time event status via an enhanced graphical user interface |
Citations (52)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6609122B1 (en) | 2000-08-01 | 2003-08-19 | Bmc Software, Inc. | Navigation of view relationships in database system |
US20050105712A1 (en) * | 2003-02-11 | 2005-05-19 | Williams David R. | Machine learning |
US7020706B2 (en) | 2002-06-17 | 2006-03-28 | Bmc Software, Inc. | Method and system for automatically updating multiple servers |
US7028301B2 (en) | 2000-12-08 | 2006-04-11 | Bmc Software, Inc. | System and method for automatic workload characterization |
US7062683B2 (en) | 2003-04-22 | 2006-06-13 | Bmc Software, Inc. | Two-phase root cause analysis |
US7131037B1 (en) | 2002-06-05 | 2006-10-31 | Proactivenet, Inc. | Method and system to correlate a specific alarm to one or more events to identify a possible cause of the alarm |
US7170864B2 (en) | 2001-03-08 | 2007-01-30 | Bmc Software, Inc. | System and method for WAP server management using a single console |
JP2009036998A (en) | 2007-08-01 | 2009-02-19 | Infocom Corp | Interactive method using computer, interactive system, computer program and computer-readable storage medium |
US7610512B2 (en) | 2006-01-06 | 2009-10-27 | Hewlett-Packard Development Company, L.P. | System and method for automated and assisted resolution of it incidents |
US7617073B2 (en) | 2002-03-01 | 2009-11-10 | Bmc Software, Inc. | System and method for assessing and indicating the health of components |
US7689628B2 (en) | 2005-05-19 | 2010-03-30 | Atul Garg | Monitoring several distributed resource elements as a resource pool |
US7716353B2 (en) | 2005-12-21 | 2010-05-11 | Bmc Software, Inc. | Web services availability cache |
US7769718B2 (en) | 2003-11-26 | 2010-08-03 | Bmc Software, Inc. | Unobtrusive point-in-time consistent copies |
US7783744B2 (en) | 2003-06-03 | 2010-08-24 | Bmc Software, Inc. | Facilitating root cause analysis for abnormal behavior of systems in a networked environment |
US7925981B2 (en) | 2003-05-14 | 2011-04-12 | Hewlett-Packard Development Company, L.P. | Systems and methods for managing web services via a framework of interfaces |
US7930396B2 (en) | 2000-07-10 | 2011-04-19 | Bmc Software, Inc. | System and method of enterprise systems and business impact management |
US7945860B2 (en) | 2003-05-14 | 2011-05-17 | Hewlett-Packard Development Company, L.P. | Systems and methods for managing conversations between information technology resources |
US7966398B2 (en) | 2001-03-30 | 2011-06-21 | Bmc Software, Inc. | Synthetic transaction monitor with replay capability |
US8051164B2 (en) | 2007-12-14 | 2011-11-01 | Bmc Software, Inc. | Impact propagation in a directed acyclic graph having restricted views |
US8224683B2 (en) | 2003-07-08 | 2012-07-17 | Hewlett-Packard Development Company, L.P. | Information technology service request level of service monitor |
US8266683B2 (en) | 2006-09-08 | 2012-09-11 | Imation Corp. | Automated security privilege setting for remote system users |
US8402127B2 (en) | 2010-06-28 | 2013-03-19 | Bmc Software, Inc. | System and method for offering virtual private clouds within a public cloud environment |
US8457928B2 (en) | 2010-03-26 | 2013-06-04 | Bmc Software, Inc. | Automatic determination of dynamic threshold for accurate detection of abnormalities |
US8478569B2 (en) | 2010-03-26 | 2013-07-02 | Bmc Software, Inc. | Auto adjustment of baseline on configuration change |
US20130268260A1 (en) | 2012-04-10 | 2013-10-10 | Artificial Solutions Iberia SL | System and methods for semiautomatic generation and tuning of natural language interaction applications |
US8612408B2 (en) | 2004-12-21 | 2013-12-17 | Bmc Software, Inc. | System and method for business service management |
US8674992B2 (en) | 2010-06-24 | 2014-03-18 | Bmc Software, Inc. | Spotlight graphs |
US8689241B2 (en) | 2011-09-30 | 2014-04-01 | Bmc Software, Inc. | Dynamic evocations for computer event management |
US8743121B2 (en) | 2009-12-23 | 2014-06-03 | Bmc Software, Inc. | Smart impact views |
US8832652B2 (en) | 2010-03-26 | 2014-09-09 | Bmc Software, Inc. | Method for customizing software applications |
US20140278413A1 (en) | 2013-03-15 | 2014-09-18 | Apple Inc. | Training an at least partial voice command system |
US8887133B2 (en) | 2006-04-28 | 2014-11-11 | Bmc Software, Inc. | Bi-directional communication between change management tool and implementation tools |
US9065783B2 (en) | 2006-08-31 | 2015-06-23 | Bmc Software, Inc. | Automated capacity provisioning method using historical performance data |
US9098322B2 (en) | 2013-03-15 | 2015-08-04 | Bmc Software, Inc. | Managing a server template |
US9122552B2 (en) | 2012-06-29 | 2015-09-01 | Bmc Software, Inc. | Hybrid cloud infrastructures |
US20150348549A1 (en) * | 2014-05-30 | 2015-12-03 | Apple Inc. | Better resolution when referencing to concepts |
US20150348565A1 (en) * | 2014-05-30 | 2015-12-03 | Apple Inc. | Determining domain salience ranking from ambiguous words in natural speech |
US20160042735A1 (en) * | 2014-08-11 | 2016-02-11 | Nuance Communications, Inc. | Dialog Flow Management In Hierarchical Task Dialogs |
US9317327B2 (en) | 2013-02-28 | 2016-04-19 | Bmc Software, Inc. | Computing infrastructure planning |
US9535737B2 (en) | 2015-01-30 | 2017-01-03 | Bladelogic, Inc. | Dynamic virtual port provisioning |
US9557969B2 (en) | 2012-03-28 | 2017-01-31 | Bmc Software, Inc. | Automated blueprint assembly for assembling an application |
US20170046124A1 (en) * | 2012-01-09 | 2017-02-16 | Interactive Voice, Inc. | Responding to Human Spoken Audio Based on User Input |
US9645833B2 (en) | 2012-12-31 | 2017-05-09 | Bmc Software, Inc. | Additive independent object modification |
US9654473B2 (en) | 2013-06-28 | 2017-05-16 | Bmc Software, Inc. | Authentication proxy agent |
US9679300B2 (en) * | 2012-12-11 | 2017-06-13 | Nuance Communications, Inc. | Systems and methods for virtual agent recommendation for multiple persons |
US9766935B2 (en) | 2009-12-30 | 2017-09-19 | Bmc Software, Inc. | Automating application provisioning for heterogeneous datacenter environments |
US9792387B2 (en) | 2001-08-31 | 2017-10-17 | Bmc Software, Inc. | Service desk data transfer interface |
US9805322B2 (en) | 2010-06-24 | 2017-10-31 | Bmc Software, Inc. | Application blueprint and deployment model for dynamic business service management (BSM) |
US20180189267A1 (en) | 2016-12-30 | 2018-07-05 | Google Inc. | Context-aware human-to-computer dialog |
JP2018185561A (en) | 2017-04-24 | 2018-11-22 | 株式会社日立製作所 | Dialogue support system, dialogue support method, and dialogue support program |
US10657961B2 (en) * | 2013-06-08 | 2020-05-19 | Apple Inc. | Interpreting and acting upon commands that involve sharing information with remote devices |
US11238850B2 (en) * | 2018-10-31 | 2022-02-01 | Walmart Apollo, Llc | Systems and methods for e-commerce API orchestration using natural language interfaces |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8959019B2 (en) * | 2002-10-31 | 2015-02-17 | Promptu Systems Corporation | Efficient empirical determination, computation, and use of acoustic confusability measures |
US9355223B2 (en) * | 2013-03-29 | 2016-05-31 | Citrix Systems, Inc. | Providing a managed browser |
WO2017083504A1 (en) * | 2015-11-12 | 2017-05-18 | Semantic Machines, Inc. | Interaction assistant |
WO2018195487A1 (en) * | 2017-04-20 | 2018-10-25 | Semantic Machines, Inc. | Automated assistant data flow |
US10394957B2 (en) * | 2017-09-25 | 2019-08-27 | Microsoft Technology Licensing, Llc | Signal analysis in a conversational scheduling assistant computing system |
GB201818237D0 (en) * | 2018-11-08 | 2018-12-26 | Polyal | A dialogue system, a dialogue method, a method of generating data for training a dialogue system, a system for generating data for training a dialogue system |
-
2019
- 2019-06-04 US US16/431,185 patent/US11790176B2/en active Active
-
2020
- 2020-03-19 WO PCT/US2020/023682 patent/WO2020191219A1/en active Application Filing
- 2020-03-19 JP JP2021556537A patent/JP7344310B2/en active Active
- 2020-03-19 KR KR1020217033770A patent/KR102623476B1/en active IP Right Grant
- 2020-03-19 AU AU2020240106A patent/AU2020240106B2/en active Active
-
2023
- 2023-09-06 US US18/462,092 patent/US20230409837A1/en active Pending
Patent Citations (57)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7930396B2 (en) | 2000-07-10 | 2011-04-19 | Bmc Software, Inc. | System and method of enterprise systems and business impact management |
US6609122B1 (en) | 2000-08-01 | 2003-08-19 | Bmc Software, Inc. | Navigation of view relationships in database system |
US7028301B2 (en) | 2000-12-08 | 2006-04-11 | Bmc Software, Inc. | System and method for automatic workload characterization |
US7170864B2 (en) | 2001-03-08 | 2007-01-30 | Bmc Software, Inc. | System and method for WAP server management using a single console |
US7966398B2 (en) | 2001-03-30 | 2011-06-21 | Bmc Software, Inc. | Synthetic transaction monitor with replay capability |
US9792387B2 (en) | 2001-08-31 | 2017-10-17 | Bmc Software, Inc. | Service desk data transfer interface |
US7617073B2 (en) | 2002-03-01 | 2009-11-10 | Bmc Software, Inc. | System and method for assessing and indicating the health of components |
US7131037B1 (en) | 2002-06-05 | 2006-10-31 | Proactivenet, Inc. | Method and system to correlate a specific alarm to one or more events to identify a possible cause of the alarm |
US7020706B2 (en) | 2002-06-17 | 2006-03-28 | Bmc Software, Inc. | Method and system for automatically updating multiple servers |
US20050105712A1 (en) * | 2003-02-11 | 2005-05-19 | Williams David R. | Machine learning |
US7062683B2 (en) | 2003-04-22 | 2006-06-13 | Bmc Software, Inc. | Two-phase root cause analysis |
US7925981B2 (en) | 2003-05-14 | 2011-04-12 | Hewlett-Packard Development Company, L.P. | Systems and methods for managing web services via a framework of interfaces |
US7945860B2 (en) | 2003-05-14 | 2011-05-17 | Hewlett-Packard Development Company, L.P. | Systems and methods for managing conversations between information technology resources |
US7783744B2 (en) | 2003-06-03 | 2010-08-24 | Bmc Software, Inc. | Facilitating root cause analysis for abnormal behavior of systems in a networked environment |
US8224683B2 (en) | 2003-07-08 | 2012-07-17 | Hewlett-Packard Development Company, L.P. | Information technology service request level of service monitor |
US7769718B2 (en) | 2003-11-26 | 2010-08-03 | Bmc Software, Inc. | Unobtrusive point-in-time consistent copies |
US8612408B2 (en) | 2004-12-21 | 2013-12-17 | Bmc Software, Inc. | System and method for business service management |
US9239857B2 (en) | 2004-12-21 | 2016-01-19 | Bmc Software, Inc. | System and method for building business service model |
US7689628B2 (en) | 2005-05-19 | 2010-03-30 | Atul Garg | Monitoring several distributed resource elements as a resource pool |
US7716353B2 (en) | 2005-12-21 | 2010-05-11 | Bmc Software, Inc. | Web services availability cache |
US7610512B2 (en) | 2006-01-06 | 2009-10-27 | Hewlett-Packard Development Company, L.P. | System and method for automated and assisted resolution of it incidents |
US7890802B2 (en) | 2006-01-06 | 2011-02-15 | Hewlett-Packard Development Company, L.P. | System and method for automated and assisted resolution of IT incidents |
US8887133B2 (en) | 2006-04-28 | 2014-11-11 | Bmc Software, Inc. | Bi-directional communication between change management tool and implementation tools |
US9065783B2 (en) | 2006-08-31 | 2015-06-23 | Bmc Software, Inc. | Automated capacity provisioning method using historical performance data |
US8266683B2 (en) | 2006-09-08 | 2012-09-11 | Imation Corp. | Automated security privilege setting for remote system users |
JP2009036998A (en) | 2007-08-01 | 2009-02-19 | Infocom Corp | Interactive method using computer, interactive system, computer program and computer-readable storage medium |
US8051164B2 (en) | 2007-12-14 | 2011-11-01 | Bmc Software, Inc. | Impact propagation in a directed acyclic graph having restricted views |
US8743121B2 (en) | 2009-12-23 | 2014-06-03 | Bmc Software, Inc. | Smart impact views |
US9766935B2 (en) | 2009-12-30 | 2017-09-19 | Bmc Software, Inc. | Automating application provisioning for heterogeneous datacenter environments |
US8457928B2 (en) | 2010-03-26 | 2013-06-04 | Bmc Software, Inc. | Automatic determination of dynamic threshold for accurate detection of abnormalities |
US8478569B2 (en) | 2010-03-26 | 2013-07-02 | Bmc Software, Inc. | Auto adjustment of baseline on configuration change |
US9363252B2 (en) | 2010-03-26 | 2016-06-07 | Bmc Software, Inc. | Method for customizing software applications |
US8832652B2 (en) | 2010-03-26 | 2014-09-09 | Bmc Software, Inc. | Method for customizing software applications |
US8674992B2 (en) | 2010-06-24 | 2014-03-18 | Bmc Software, Inc. | Spotlight graphs |
US9805322B2 (en) | 2010-06-24 | 2017-10-31 | Bmc Software, Inc. | Application blueprint and deployment model for dynamic business service management (BSM) |
US8402127B2 (en) | 2010-06-28 | 2013-03-19 | Bmc Software, Inc. | System and method for offering virtual private clouds within a public cloud environment |
US8689241B2 (en) | 2011-09-30 | 2014-04-01 | Bmc Software, Inc. | Dynamic evocations for computer event management |
US20170046124A1 (en) * | 2012-01-09 | 2017-02-16 | Interactive Voice, Inc. | Responding to Human Spoken Audio Based on User Input |
US9557969B2 (en) | 2012-03-28 | 2017-01-31 | Bmc Software, Inc. | Automated blueprint assembly for assembling an application |
US20130268260A1 (en) | 2012-04-10 | 2013-10-10 | Artificial Solutions Iberia SL | System and methods for semiautomatic generation and tuning of natural language interaction applications |
US9122552B2 (en) | 2012-06-29 | 2015-09-01 | Bmc Software, Inc. | Hybrid cloud infrastructures |
US9679300B2 (en) * | 2012-12-11 | 2017-06-13 | Nuance Communications, Inc. | Systems and methods for virtual agent recommendation for multiple persons |
US9645833B2 (en) | 2012-12-31 | 2017-05-09 | Bmc Software, Inc. | Additive independent object modification |
US9317327B2 (en) | 2013-02-28 | 2016-04-19 | Bmc Software, Inc. | Computing infrastructure planning |
US9922642B2 (en) * | 2013-03-15 | 2018-03-20 | Apple Inc. | Training an at least partial voice command system |
US20140278413A1 (en) | 2013-03-15 | 2014-09-18 | Apple Inc. | Training an at least partial voice command system |
US9098322B2 (en) | 2013-03-15 | 2015-08-04 | Bmc Software, Inc. | Managing a server template |
US10657961B2 (en) * | 2013-06-08 | 2020-05-19 | Apple Inc. | Interpreting and acting upon commands that involve sharing information with remote devices |
US9654473B2 (en) | 2013-06-28 | 2017-05-16 | Bmc Software, Inc. | Authentication proxy agent |
US9633004B2 (en) * | 2014-05-30 | 2017-04-25 | Apple Inc. | Better resolution when referencing to concepts |
US20150348565A1 (en) * | 2014-05-30 | 2015-12-03 | Apple Inc. | Determining domain salience ranking from ambiguous words in natural speech |
US20150348549A1 (en) * | 2014-05-30 | 2015-12-03 | Apple Inc. | Better resolution when referencing to concepts |
US20160042735A1 (en) * | 2014-08-11 | 2016-02-11 | Nuance Communications, Inc. | Dialog Flow Management In Hierarchical Task Dialogs |
US9535737B2 (en) | 2015-01-30 | 2017-01-03 | Bladelogic, Inc. | Dynamic virtual port provisioning |
US20180189267A1 (en) | 2016-12-30 | 2018-07-05 | Google Inc. | Context-aware human-to-computer dialog |
JP2018185561A (en) | 2017-04-24 | 2018-11-22 | 株式会社日立製作所 | Dialogue support system, dialogue support method, and dialogue support program |
US11238850B2 (en) * | 2018-10-31 | 2022-02-01 | Walmart Apollo, Llc | Systems and methods for e-commerce API orchestration using natural language interfaces |
Non-Patent Citations (5)
Title |
---|
International Search Report and Written Opinion for PCT Application No. PCT/US2020/023682 dated Jul. 3, 2020; 10 pgs. |
Japanese Patent Application for Japanese Patent Application No. 2021-556537 dated Feb. 7, 2023; 6 pgs. |
U.S. Appl. No. 16/247,190, filed Jan. 14, 2019, Asba et al. |
U.S. Appl. No. 16/255,671, filed Jan. 23, 2019, Asba et al. |
U.S. Appl. No. 62/820,730, filed Mar. 19, 2019, Asba et al. |
Also Published As
Publication number | Publication date |
---|---|
KR20210138095A (en) | 2021-11-18 |
KR102623476B1 (en) | 2024-01-09 |
JP7344310B2 (en) | 2023-09-13 |
JP2022525480A (en) | 2022-05-16 |
WO2020191219A1 (en) | 2020-09-24 |
AU2020240106B2 (en) | 2022-12-08 |
AU2020240106A1 (en) | 2021-10-14 |
US20200302020A1 (en) | 2020-09-24 |
US20230409837A1 (en) | 2023-12-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11790176B2 (en) | Systems and methods for a virtual agent in a cloud computing environment | |
US20210342547A1 (en) | System for focused conversation context management in a reasoning agent/behavior engine of an agent automation system | |
US11423910B2 (en) | Systems and method for third party natural language understanding service integration | |
US11736418B2 (en) | Decision tree processing for chatbot dialog flow | |
KR102601615B1 (en) | dynamic translation | |
US20230141398A1 (en) | Data augmentation for intent classification | |
US20220131816A1 (en) | Virtual agent portal integration of two frameworks | |
US11112939B2 (en) | Dynamic updates for configurable menu items | |
US20200192686A1 (en) | Customer service management | |
US11513823B2 (en) | Chat interface for resource management | |
JP7296476B2 (en) | Action decisions for case management | |
US20220004407A1 (en) | System and method for simple object access protocol (soap) interface creation | |
US11127402B2 (en) | Systems and methods for voice development frameworks | |
US11442899B2 (en) | Systems and methods for improved application programing interface (API) retry handling | |
US20220230181A1 (en) | Next best action framework with nested decision trees | |
US11250202B2 (en) | System and method for large volume data streaming as a service | |
US20200302369A1 (en) | Systems and method for work item skill determination |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: SERVICENOW, INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:ABU ASBA, NABIL;GRIFFIN, MARK DAVID;JAIN, ANUJ;SIGNING DATES FROM 20190528 TO 20190603;REEL/FRAME:049364/0448 |
|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE AFTER FINAL ACTION FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: ADVISORY ACTION MAILED |
|
STCV | Information on status: appeal procedure |
Free format text: NOTICE OF APPEAL FILED |
|
STCV | Information on status: appeal procedure |
Free format text: APPEAL BRIEF (OR SUPPLEMENTAL BRIEF) ENTERED AND FORWARDED TO EXAMINER |
|
STCV | Information on status: appeal procedure |
Free format text: EXAMINER'S ANSWER TO APPEAL BRIEF MAILED |
|
STCV | Information on status: appeal procedure |
Free format text: ON APPEAL -- AWAITING DECISION BY THE BOARD OF APPEALS |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: AWAITING TC RESP, ISSUE FEE PAYMENT VERIFIED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |